1. 6/29/1999PDPTA'991 Performance Prediction for Large Scale Parallel Systems Yuhong Wen and Geoffrey C. Fox Northeast Parallel Architecture Center (NPAC) Syracuse University {wen,gcf}@npac.syr.edu

2. 6/29/1999PDPTA'992 Why Performance Prediction? Application complexities A lot of processors required Large amount of data involved Time-consuming processing Performance prediction to fasten –new parallel computer architecture design –application model design

3. 6/29/1999PDPTA'993 Performance Prediction Approaches Concept design level performance prediction –aim to provide a quick and roughly correct performance prediction at the early stage of model design –PetaSIM based on this level Detailed performance prediction –to provide detailed information of a given application running on specific computer system -- Simulation

4. 6/29/1999PDPTA'994 PetaSIM Motivation PetaSIM was designed to allow “qualitative” performance estimates” where in particular the design of machine is particularly easy to change The project will build up a suite of applications which can be used in future activities such as “Petaflop” architectures studies Applications are to be derived “by hand” or by automatic generation from Maryland Application Emulators Special attention to support of hierarchical memory machines and data intensive applications Support parallelism and representation at different grain sizes Support simulation of “pure data-parallel” and composition of linked modules

5. 6/29/1999PDPTA'995 Performance Prediction Process Estimated Performance PetaSIM Estimator Execution Script Architecture Description PSL Specification Existing Real Applications Application Emulators Detailed Simulators Cost Model

6. 6/29/1999PDPTA'996 Full Heterogeneous MetaProblem Module Aggregate Loosely Synchronize Computation Module Components Task Parallelism Data Parallelism Splitting into Lower Level Memory Hierarchy PetaSIM Peta-Computing Hierarchy Simulate Real Computing

7. 6/29/1999PDPTA'997 Performance Prediction Model Hardware Domain Application Domain Software / Operating System Domain Multi Domain model

8. 6/29/1999PDPTA'998 Three Domain Performance Prediction Application Domain –to extract the data aggregates –to give abstract data movement and computation behavior Software / Operating System Domain –to provide the methods for task process and memory management, communication and parallel file access Hardware Domain –to provide the model of processor and memory components, includes cache as well

9. 6/29/1999PDPTA'999 Performance Specification Language Various different kinds of applications Different kinds of parallel architectures Because of the complexities of performance prediction It’s very important to design a general performance specification language (PSL) to represent all the features of the different aspects in the performance process. PetaSIM shows an initial step to suggest that characteristics of such a Performance Specification Language (PSL).

10. 6/29/1999PDPTA'9910 Performance Specification Language The size of each data block the number of data blocks the amount of data operations in the data block data distribution model data processing sequence / flow of the data blocks -- the application algorithm Application Domain

11. 6/29/1999PDPTA'9911 Performance Specification Language The memory management approach the cache management approach parallel task schedule method parallel file access pattern computing, communication overlap approach Software / Operating System Domain

12. 6/29/1999PDPTA'9912 Performance Specification Language Computing capability of each processor, which include the CPU speed and the bandwidth memory size and cache size architecture of each processing node inter-communication topology of the parallel machines, which is to provide the information of communication between the processors Hardware Domain

13. 6/29/1999PDPTA'9913 Petasim Estimator & Emulator PetaSIM Performance Estimation Nodeset Linkset Dataset Distribution UMD Emulators Execution Script Hand Code Applications

14. 6/29/1999PDPTA'9914 Emulators Extract the application’s computational and data access patterns A simplified version of the real application, contains all the necessary communication, computation and I/O characteristics less accurate than full application, but more robust fast performance prediction for rapid prototyping

15. 6/29/1999PDPTA'9915 PetaSIM Design We define an object structure for computer (including network) and data Architecture Description –nodeset & linkset –(describe the architecture memory hierarchy) Data Description –dataset & distribution Application Description –execution script System / Software Description

16. 6/29/1999PDPTA'9916 Architecture Description A nodeset is a collection of entities with types liked –memory with cache & disks –CPU where results can be calculated –pathway such as bus, switch or network A linkset connects nodesets together in various ways

17. 6/29/1999PDPTA'9917 Application Description An application consists of dataset objects dataset implementation is controled by the distribution objects application behavior is represented by execution script –a set of command statements –data movements –data computation –synchronization

18. 6/29/1999PDPTA'9918 Nodeset Object Structure Name: one per nodeset object type: choose from memory, cache, disk, CPU, pathway number: number of members of this nodeset in the architecture grainsize: size in bytes of each member of this nodeset (for memory, cache, disk) bandwidth: maximum bandwidth allowed in any one member of this nodeset floatspeed: CPU’s float calculating speed calculate(): method used by CPU nodeset to perform computation cacherule: controls persistence of data in a memory or cache portcount: number of ports on each member of nodeset portname[]: ports connected to linkset portlink[]: name of linkset connecting to this port nodeset_member_list: list of nodeset members in this nodeset (for nodeset member identification)

19. 6/29/1999PDPTA'9919 Linkset Object Structure Name: one per linkset object type: choose from updown, across nodesetbegin: name of initial nodeset joined by this linkset nodesetend: name of final nodeset joined buy this linkset topology: used for across networks to specify linkage between members of a single nodeset duplex: choose from full or half number: number of members of this linkset in the architecture latency: time to send zero length message across any member of linkset bandwidth: maximum bandwidth allowed in any link of this linkset send(): method that calculates cost of sending a message across the linkset distribution: name of geometric distribution controlling this linkset linkset_member_list: list of linkset members in this linkset ( for linkset member identification )

20. 6/29/1999PDPTA'9920 Dataset Object Structure Name: one per dataset object choose from grid1dim, grid2dim, grid3dim, specifies type of dataset bytesperunit: number of bytes in each unit floatsperunit: update cost as a floating point arithmetic count operationsperunit: operations in each unit update(): method that updates given dataset which is contained in a CPU nodeset and a grainsize controlled by last memory nodeset visited transmit(): method that calculates cost of transmission of dataset between memory levels either communication or movement up and down hierarchy –Methods can use other parameters or be custom

21. 6/29/1999PDPTA'9921 Execution Script Currently a few primitives which stress (unlike most languages) movement of data through memory hierarchies send DATAFAMILY from MEM-LEVEL-L to MEM-LEVEL-K –These reference object names for data and memory nodesets move DATAFAMILY from MEM-LEVEL-L to MEM-LEVEL-K Use distribution DISTRIBUTION from MEM-LEVEL-L to MEM-LEVEL-K compute DATAFAMILY-A, DATAFAMILY-B,… on MEM- LEVEL-L synchronize (synchronizes all processors --- loosely synchronous barrier) loop operation

22. 6/29/1999PDPTA'9922 PetaSIM Estimation Schedule Each nodeset member has its usage control to record when dataset arrives and when to send out to next nodeset member Each linkset member has its usage control to record at what time the linkset member is free or occupied Data Driven model: Ready ---> Go (First come, First Service) Support Both data parallel mode and individual operation on each nodeset, linkset member mode

23. 6/29/1999PDPTA'9923 Architecture of PetaSIM C++ Simulator Multi-User Java Server Standard Java Applet Client

24. 6/29/1999PDPTA'9924 Pathfinder Performance Estimation Results

25. 6/29/1999PDPTA'9925 Pathfinder Estimation Results II

26. 6/29/1999PDPTA'9926 Titan Estimation Results (Fixed)

27. 6/29/1999PDPTA'9927 VMScope Estimation Results

28. 6/29/1999PDPTA'9928 PetaSIM Features Accurate estimation Friendly user interface –Easy to modify the architecture design –Easy to monitor the effect of the design change Fast Estimation Detail performance estimation –Provide detail usage of each individual nodeset and linkset member in the memory hierarchy

29. 6/29/1999PDPTA'9929 Compare with some other Simulators Different Simulation Approach –PetaSIM not real run the application, estimate the execution script (operation abstraction) PetaSIM running on single processor Similar performance estimation results PetaSIM can easily deal with different kinds of computer architecture PetaSIM can get detailed information of any part of the architecture

30. 6/29/1999PDPTA'9930 PetaSIM Current Progress Summary Architecture Description (nodeset & linkset) Application Description (dataset & execution script) Link to Application Emulators Jacobi hand-written example Pathfinder, Titan, VMScope real applications (Generated by UMD’s Emulator) Easy modified Architecture and Application description Fast and relatively Accurate performance estimation (PetaSIM running on single processor) Java applet based user Interface Data Parallel Model & Individual Control

31. 6/29/1999PDPTA'9931 Possible Future Work Richer set of applications using standard benchmarks and DoD MSTAR Relate object model to those used in “seamless interfaces” / metacomputing i.e. to efforts to establish (distributed) object model for computation Review very simple execution script -- should we add more complex primitives or regard “application emulators” as this complex script Binary format (“compiled PetaSIM”) of architecture and application description ( ASCII format will make execution script very large) –Translation tool from ASCII format to binary format (to retain the friendly user interface) Upgrade performance evaluation model Run performance simulation in parallel (i.e. PetaSIM running on multi-processors)

32. 6/29/1999PDPTA'9932 PetaSIM Web-Site URL http://kopernik.npac.syr.edu:4096/petasim/V1.0/PetaSIM.html -- PetaSIM Java Applet front user interface and demo -- Related PetaSIM documents

33. 6/29/1999PDPTA'9933 Interface of PetaSIM Client